Hugging Face's logo

CocosNucifera
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
CocosNucifera commited on
Commit
f5a25e5
•
1 Parent(s): 8fb3458

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +4 -4
  2. args.yml +1 -1
  3. config.yml +3 -3
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +1 -1
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. replay.mp4 +2 -2
  9. results.json +1 -1
  10. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 588.50 +/- 228.64
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,15 +62,15 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 32),
66
- ('buffer_size', 150000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.0003),
74
  ('learning_starts', 100000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 551.00 +/- 126.49
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 64),
66
+ ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 3.86e-05),
74
  ('learning_starts', 100000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 170520487
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1831186370
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,8 +1,8 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 32
4
  - - buffer_size
5
- - 150000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0003
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
+ - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 3.86e-05
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c2e1f491f663475ba7691595a9991cae4636faa5edf37cfb2f5726ec22e87f3
3
  size 27220208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19bb5d6647829c410ba278f4fc3daa1ea54f017dadaae2c2ce089f0731017b68
3
  size 27220208
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38e5f52f10d94bd766d76ce625e6c3a14100254421ccb63031e49f4c13df74f9
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:383855ba28fa42d5f6224d992cea3a54191c3e8e26a77927d5988fc24186da1d
3
  size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be710b45964163298c4b723006570f69c43fb25e9bbcf11668057d060141c31b
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dbc983e69ad730d870690951a08366909cb99c5dbc0c11c94594464c45b5be7
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b16f37d9a437284899ca8b5aabbfe502eb8f5c48c1eed5c702a0b5ad77e9e503
3
- size 251742
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06aa0e54180139fe372c80a8037c97e3eb6f84beb99b2f03a6b242e9bd31be81
3
+ size 195697
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 588.5, "std_reward": 228.63781402034093, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-27T08:15:55.727389"}
 
1
+ {"mean_reward": 551.0, "std_reward": 126.4871534978948, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-06T13:50:32.535537"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1ffc30f61860919636ac07dabcef2917bce7eede5a31d7bb433858097eb9a0c
3
- size 35041
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81ae47ad8a95f1d0132826031fa9494249cf7ab3a218a2802e6cc204b863d950
3
+ size 41151